Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1851. Min Range: -7.1851
Max Act: 7.1851. Min Act: -0.1700
Data Index: 6395837 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9976. Min Act: -0.1700
Data Index: 5544888 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9663. Min Act: -0.1700
Data Index: 4724933 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9663. Min Act: -0.1700
Data Index: 89629 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9351. Min Act: -0.1700
Data Index: 3601371 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1775773 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.9038. Min Act: -0.1700
Data Index: 372329 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8726. Min Act: -0.1700
Data Index: 6997479 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8726. Min Act: -0.1700
Data Index: 2175294 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8413. Min Act: -0.1700
Data Index: 1288954 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8101. Min Act: -0.1700
Data Index: 6913308 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8413. Min Act: -0.1700
Data Index: 7784413 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.8101. Min Act: -0.1700
Data Index: 6247429 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 5759084 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 5764052 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 2498569 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 7479166 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 1765282 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 7479172 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1851. Min Range: -7.1851
Max Act: 6.7788. Min Act: -0.1700
Data Index: 2901290 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19